US 12,141,618 B1
Dynamic generation and presentation of load records for load allocation
Philip Mark Kaminsky, El Cerrito, CA (US); Mohammadmohsen Moarefdoost, Seattle, WA (US); Priyanka Prakash Mhatre, Seattle, WA (US); Dorothy Mary Watts, Seattle, WA (US); Ruchit Aswin Shah, Bothell, WA (US); Ankur Gupta, Delhi (IN); Subhadeep Gupta, Burdwan (IN); Vishal Verma, Faridabad (IN); and Niels Krohn, Seattle, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Oct. 27, 2021, as Appl. No. 17/512,002.
Int. Cl. G06F 9/50 (2006.01); G06F 16/9035 (2019.01); G06F 16/9038 (2019.01)
CPC G06F 9/505 (2013.01) [G06F 16/9035 (2019.01); G06F 16/9038 (2019.01)] 20 Claims
OG exemplary drawing
 
1. One or more non-transitory computer-readable media comprising computer executable instructions that, when executed by one or more processors of a computer system, cause the computer system to perform operations comprising:
providing, at a first time, a plurality of load records for presentation in a load acceptance user interface at a first plurality of user devices associated with a first plurality of users, the load acceptance user interface providing:
a search section for searching a plurality of loads represented by the plurality of load records; and
an acceptance section for viewing and accepting the plurality of loads, the acceptance section presenting a first value of an attribute of each load record;
collecting contextual information representing interactions of the first plurality of users using the search section and the acceptance section to interact with at least some load records of the plurality of load records, the contextual information indicative of user supply with respect to individual loads of the plurality of loads presented using the load acceptance user interface at the first time;
providing the contextual information as input to a machine learning model configured to output, for each load record of the plurality of load records, an acceptance prediction indicating, for a set of values of the attribute, a probability that a respective load corresponding to the respective load record will be accepted by any user;
determining, for a particular load record of the plurality of load records, a sequence of values of the attribute based at least in part on the acceptance prediction for the particular load record; and
responsive to determining the sequence of values, updating, at a second time, the load acceptance user interface to present the plurality of load records within the load acceptance user interface at a second plurality of user devices associated with a second plurality of users, the load acceptance user interface presenting a first value of the sequence of values of the attribute at the second time.